How do you run trillion-parameter AI models and rapidly switch between multiple AI agents without hitting the traditional memory wall?
Sumti Jairath, Chief Architect at SambaNova Systems, explains how memory-centric design and RDU dataflow architecture change the way large-scale GenAI and agentic workloads are executed.
What does the next generation of AI infrastructure look like inside the world's largest banks?
Why are major financial institutions looking beyond conventional GPU infrastructure, and what makes SambaNova's SN50 and RDU architecture different?
Can sophisticated agentic AI workflows for healthcare run on a single system?
See how SambaStack combines Agentic AI and GraphRAG for Electronic Health Records, demonstrating how complex healthcare information can be retrieved, connected and analysed within a single-node environment.
Why does agentic AI place different demands on the infrastructure running the model?
Pushkar Nandkar explores SambaNova's SN40L and explains how dataflow architecture can deliver the inference performance needed when AI moves beyond individual prompts into complex, multi-stage agentic workflows.
Artificial Intelligence is often framed as potential, but its real value depends on cost, control, and deployment. This video explores the infrastructure challenges behind large-scale AI and outlines a more efficient, sovereign approach. At Argyll Data Development, we focus on making AI work in practice.
